© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 194
    Prev
    Next
    INDEX
    Explanations

    scientific publications and citations using volume, page, year, and author formats

    oai_token-act-pair · gemini-2.0-flash

    dashes and commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     démocr
    -1.09
     fermés
    -1.05
     sauvages
    -1.02
     colorés
    -1.02
     scolaires
    -1.02
     définiti
    -1.00
     médicaux
    -1.00
     normaux
    -0.98
     africains
    -0.97
     precisione
    -0.96
    POSITIVE LOGITS
    fl
    0.32
    ​​​​
    0.30
    circa
    0.30
    ⁠
    0.30
    . 
    0.30
    [-]
    0.28
    ¹,
    0.28
    PageFactory
    0.28
     Ã
    0.27
    ​.
    0.27
    Activations Density 25.900%

    No Known Activations